syssec-utd/py313-pylingual-v1.1-statement

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

py313-pylingual-v1.1-statement

This model is a fine-tuned version of Salesforce/codet5-base on the syssec-utd/statement-py313-pylingual-v2-tokenized dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 2e-05
• —trainbatchsize: 24
• —evalbatchsize: 24
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 3
• —totaltrainbatch_size: 72
• —totalevalbatch_size: 72
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 2
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.46.1
• —Pytorch 2.4.1+cu121
• —Datasets 3.0.1
• —Tokenizers 0.20.3